FA-GAN: Face Augmentation GAN for Deformation-Invariant Face Recognition
文献类型:期刊论文
; | |
作者 | Luo, Mandi1,2,3; Cao, Jie1,2,3; Ma, Xin1,2,3; Zhang, Xiaoyu4; He, Ran1,2,3 |
刊名 | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY ; IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY |
出版日期 | 2021 ; 2021 |
卷号 | 16期号:0页码:2341-2355 |
ISSN号 | 1556-6013 ; 1556-6013 |
关键词 | Face recognition Face recognition Strain Geometry Frequency division multiplexing Training Task analysis Semantics Face augmentation deformation-invariant face recognition face disentanglement graph convolutional networks Strain Geometry Frequency division multiplexing Training Task analysis Semantics Face augmentation deformation-invariant face recognition face disentanglement graph convolutional networks |
DOI | 10.1109/TIFS.2021.3053460 ; 10.1109/TIFS.2021.3053460 |
英文摘要 | Substantial improvements have been achieved in the field of face recognition due to the successful application of deep neural networks. However, existing methods are sensitive to both the quality and quantity of the training data. Despite the availability of large-scale datasets, the long tail data distribution induces strong biases in model learning. In this paper, we present a Face Augmentation Generative Adversarial Network (FA-GAN) to reduce the influence of imbalanced deformation attribute distributions. We propose to decouple these attributes from the identity representation with a novel hierarchical disentanglement module. Moreover, Graph Convolutional Networks (GCNs) are applied to recover geometric information by exploring the interrelations among local regions to guarantee the preservation of identities in face data augmentation. Extensive experiments on face reconstruction, face manipulation, and face recognition demonstrate the effectiveness and generalization ability of the proposed method. ;Substantial improvements have been achieved in the field of face recognition due to the successful application of deep neural networks. However, existing methods are sensitive to both the quality and quantity of the training data. Despite the availability of large-scale datasets, the long tail data distribution induces strong biases in model learning. In this paper, we present a Face Augmentation Generative Adversarial Network (FA-GAN) to reduce the influence of imbalanced deformation attribute distributions. We propose to decouple these attributes from the identity representation with a novel hierarchical disentanglement module. Moreover, Graph Convolutional Networks (GCNs) are applied to recover geometric information by exploring the interrelations among local regions to guarantee the preservation of identities in face data augmentation. Extensive experiments on face reconstruction, face manipulation, and face recognition demonstrate the effectiveness and generalization ability of the proposed method. |
资助项目 | Beijing Natural Science Foundation[JQ18017] ; Beijing Natural Science Foundation[JQ18017] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U20A20223] ; National Natural Science Foundation of China[U2003111] ; Youth Innovation Promotion Association CAS[Y201929] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U20A20223] ; National Natural Science Foundation of China[U2003111] ; Youth Innovation Promotion Association CAS[Y201929] |
WOS研究方向 | Computer Science ; Computer Science ; Engineering ; Engineering |
语种 | 英语 ; 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC ; IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000621404700005 ; WOS:000621404700005 |
资助机构 | Beijing Natural Science Foundation ; Beijing Natural Science Foundation ; National Natural Science Foundation of China ; Youth Innovation Promotion Association CAS ; National Natural Science Foundation of China ; Youth Innovation Promotion Association CAS |
源URL | [http://ir.ia.ac.cn/handle/173211/44012] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Zhang, Xiaoyu |
作者单位 | 1.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 4.Chinese Acad Sci, Inst Informat Engn, Beijing 100093, Peoples R China |
推荐引用方式 GB/T 7714 | Luo, Mandi,Cao, Jie,Ma, Xin,et al. FA-GAN: Face Augmentation GAN for Deformation-Invariant Face Recognition, FA-GAN: Face Augmentation GAN for Deformation-Invariant Face Recognition[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2021, 2021,16, 16(0):2341-2355, 2341-2355. |
APA | Luo, Mandi,Cao, Jie,Ma, Xin,Zhang, Xiaoyu,&He, Ran.(2021).FA-GAN: Face Augmentation GAN for Deformation-Invariant Face Recognition.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,16(0),2341-2355. |
MLA | Luo, Mandi,et al."FA-GAN: Face Augmentation GAN for Deformation-Invariant Face Recognition".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 16.0(2021):2341-2355. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。